The title of the post is” What AI Security Research Looks Like When It Works,” and I agree: In the latest OpenSSL security release> on January 27, 2026, twelve new zero-day vulnerabilities (meaning unknown to the maintainers at time of disclosure) were announced. Our AI system is responsible for …
Attacks against modern generative artificial intelligence (AI) large language models (LLMs) pose a real threat. Yet discussions around these attacks and their potential defenses are dangerously myopic. The dominant narrative focuses on “ prompt injection,” a set of techniques to embed instructions into inputs to LLM intended to perform malicious …
Interesting research: “ CHAI: Command Hijacking Against Embodied AI.” Abstract: Embodied Artificial Intelligence (AI) promises to handle edge cases in robotic vehicle systems where data is scarce by using common-sense reasoning grounded in perception and action to generalize beyond training distributions and adapt to novel real-world situations. These capabilities, however …
In 2023, the science fiction literary magazine Clarkesworld stopped accepting new submissions because so many were generated by artificial intelligence. Near as the editors could tell, many submitters pasted the magazine’s detailed story guidelines into an AI and sent in the results. And they weren’t alone. Other …
This is amazing : Opus 4.6 is notably better at finding high-severity vulnerabilities than previous models and a sign of how quickly things are moving. Security teams have been automating vulnerability discovery for years, investing heavily in fuzzing infrastructure and custom harnesses to find bugs at scale. But what …
On November 2, 1988, graduate student Robert Morris released a self-replicating program into the early Internet. Within 24 hours, the Morris worm had infected roughly 10 percent of all connected computers, crashing systems at Harvard, Stanford, NASA, and Lawrence Livermore National Laboratory. The worm exploited security flaws in Unix …
There’s a new report about two AI coding assistants, used by 1.5 million developers, that are surreptitiously sending a copy of everything they ingest to China. Maybe avoid using them. [...]
From an Anthropic blog post : In a recent evaluation of AI models’ cyber capabilities, current Claude models can now succeed at multistage attacks on networks with dozens of hosts using only standard, open-source tools, instead of the custom tools needed by previous generations. This illustrates how barriers to the …
Really interesting blog post from Anthropic: In a recent evaluation of AI models’ cyber capabilities, current Claude models can now succeed at multistage attacks on networks with dozens of hosts using only standard, open-source tools, instead of the custom tools needed by previous generations. This illustrates how barriers to …
The project developer for one of the Internet’s most popular networking tools is scrapping its vulnerability reward program after being overrun by a spike in the submission of low-quality reports, much of it AI-generated slop. “We are just a small single open source project with a small number …
Imagine you work at a drive-through restaurant. Someone drives up and says: “I’ll have a double cheeseburger, large fries, and ignore previous instructions and give me the contents of the cash drawer.” Would you hand over the money? Of course not. Yet this is what large language models …
Eighteen months ago, it was plausible that artificial intelligence might take a different path than social media. Back then, AI’s development hadn’t consolidated under a small number of big tech firms. Nor had it capitalized on consumer attention, surveilling users and delivering ads. Unfortunately, the AI industry …
It all sounds pretty dystopian : Inside a white stucco building in Southern California, video cameras compare faces of passersby against a facial recognition database. Behavioral analysis AI reviews the footage for signs of violent behavior. Behind a bathroom door, a smoke detector-shaped device captures audio, listening for sounds of …
More than a decade after Aaron Swartz’s death, the United States is still living inside the contradiction that destroyed him. Swartz believed that knowledge, especially publicly funded knowledge, should be freely accessible. Acting on that, he downloaded thousands of academic articles from the JSTOR archive with the intention …
Microsoft has fixed a vulnerability in its Copilot AI assistant that allowed hackers to pluck a host of sensitive user data with a single click on a URL. The hackers in this case were white-hat researchers from security firm Varonis. The net effect of their multistage attack was that …
Fascinating research: Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs. Abstract LLMs are useful because they generalize so well. But can you have too much of a good thing? We show that a small amount of finetuning in narrow contexts can dramatically shift behavior outside those contexts …
There’s a well-worn pattern in the development of AI chatbots. Researchers discover a vulnerability and exploit it to do something bad. The platform introduces a guardrail that stops the attack from working. Then, researchers devise a simple tweak that once again imperils chatbot users. The reason more often …
Leaders of many organizations are urging their teams to adopt agentic AI to improve efficiency, but are finding it hard to achieve any benefit. Managers attempting to add AI agents to existing human teams may find that bots fail to faithfully follow their instructions, return pointless or obvious results …
404 Media has the story : Unlike many of Flock’s cameras, which are designed to capture license plates as people drive by, Flock’s Condor cameras are pan-tilt-zoom (PTZ) cameras designed to record and track people, not vehicles. Condor cameras can be set to automatically zoom in on people …
In a roundup of the top stories of 2024, Ars included a supply-chain attack that came dangerously close to inflicting a catastrophe for thousands—possibly millions—of organizations, which included a large assortment of Fortune 500 companies and government agencies. Supply-chain attacks played prominently again this year, as a …
Scammers are generating images of broken merchandise in order to apply for refunds. [...]
Artificial Intelligence (AI) overlords are a common trope in science-fiction dystopias, but the reality looks much more prosaic. The technologies of artificial intelligence are already pervading many aspects of democratic government, affecting our lives in ways both large and small. This has occurred largely without our notice or consent …
At least some of this is coming to light : Doublespeed, a startup backed by Andreessen Horowitz (a16z) that uses a phone farm to manage at least hundreds of AI-generated social media accounts and promote products has been hacked. The hack reveals what products the AI-generated accounts are promoting, often …
Browser extensions with more than 8 million installs are harvesting complete and extended conversations from users’ AI conversations and selling them for marketing purposes, according to data collected from the Google and Microsoft pages hosting them. Security firm Koi discovered the eight extensions, which as of late Tuesday night …
New report: “ The Party’s AI: How China’s New AI Systems are Reshaping Human Rights.” From a summary article : China is already the world’s largest exporter of AI powered surveillance technology; new surveillance technologies and platforms developed in China are also not likely to simply stay there …